Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 3678 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.8187. Min Range: -0.8187

Max Act: 0.7662. Min Act: 0.0000

Data Index: 644600 (C4 (Web Text))

Max Activating Token Index: 887

Text #1

Max Range: 0.8187. Min Range: -0.8187

Max Act: 0.8187. Min Act: -0.0000

Data Index: 377103 (C4 (Web Text))

Max Activating Token Index: 362

Text #2

Max Range: 0.8187. Min Range: -0.8187

Max Act: 0.7014. Min Act: -0.0000

Data Index: 379291 (C4 (Web Text))

Max Activating Token Index: 1022

Text #3

Max Range: 0.8187. Min Range: -0.8187

Max Act: 0.6570. Min Act: -0.0000

Data Index: 552141 (C4 (Web Text))

Max Activating Token Index: 931

Text #4

Max Range: 0.8187. Min Range: -0.8187

Max Act: 0.6059. Min Act: -0.0000

Data Index: 1532892 (Python Code)

Max Activating Token Index: 531

Text #5

Max Range: 0.8187. Min Range: -0.8187

Max Act: 0.5893. Min Act: -0.0000

Data Index: 212255 (C4 (Web Text))

Max Activating Token Index: 690

Text #6

Max Range: 0.8187. Min Range: -0.8187

Max Act: 0.5847. Min Act: -0.0000

Data Index: 1282982 (C4 (Web Text))

Max Activating Token Index: 792

Text #7

Max Range: 0.8187. Min Range: -0.8187

Max Act: 0.6026. Min Act: -0.0000

Data Index: 1048092 (C4 (Web Text))

Max Activating Token Index: 213

Text #8

Max Range: 0.8187. Min Range: -0.8187

Max Act: 0.5811. Min Act: 0.0000

Data Index: 1112902 (C4 (Web Text))

Max Activating Token Index: 412

Text #9

Max Range: 0.8187. Min Range: -0.8187

Max Act: 0.4946. Min Act: -0.0000

Data Index: 1278440 (C4 (Web Text))

Max Activating Token Index: 283

Text #10

Max Range: 0.8187. Min Range: -0.8187

Max Act: 0.5269. Min Act: 0.0000

Data Index: 509589 (C4 (Web Text))

Max Activating Token Index: 573

Text #11

Max Range: 0.8187. Min Range: -0.8187

Max Act: 0.4779. Min Act: -0.0000

Data Index: 1307624 (C4 (Web Text))

Max Activating Token Index: 993

Text #12

Max Range: 0.8187. Min Range: -0.8187

Max Act: 0.4900. Min Act: 0.0000

Data Index: 763256 (C4 (Web Text))

Max Activating Token Index: 61

Text #13

Max Range: 0.8187. Min Range: -0.8187

Max Act: 0.4868. Min Act: -0.0000

Data Index: 872566 (C4 (Web Text))

Max Activating Token Index: 662

Text #14

Max Range: 0.8187. Min Range: -0.8187

Max Act: 0.4891. Min Act: 0.0000

Data Index: 1337906 (C4 (Web Text))

Max Activating Token Index: 360

Text #15

Max Range: 0.8187. Min Range: -0.8187

Max Act: 0.4837. Min Act: -0.0000

Data Index: 684864 (C4 (Web Text))

Max Activating Token Index: 782

Text #16

Max Range: 0.8187. Min Range: -0.8187

Max Act: 0.4789. Min Act: -0.0000

Data Index: 171606 (C4 (Web Text))

Max Activating Token Index: 975

Text #17

Max Range: 0.8187. Min Range: -0.8187

Max Act: 0.4454. Min Act: -0.0000

Data Index: 445006 (C4 (Web Text))

Max Activating Token Index: 781

Text #18

Max Range: 0.8187. Min Range: -0.8187

Max Act: 0.4596. Min Act: 0.0000

Data Index: 676942 (C4 (Web Text))

Max Activating Token Index: 910

Text #19

Max Range: 0.8187. Min Range: -0.8187

Max Act: 0.4501. Min Act: 0.0000

Data Index: 155578 (C4 (Web Text))

Max Activating Token Index: 995